Aramco's VC Arm Backs Resemble AI in Deepfake Detection Push
Wa'ed Ventures, Saudi Aramco's venture capital arm, has invested in Resemble AI, a US company developing voice cloning and deepfake detection technology.
New Hierarchical Model Improves Real-Time Conversational AI Turn-
Researchers introduce a hierarchical end-of-turn detection model with primary speaker segmentation, advancing real-time conversational AI systems for more natural voice interactions.
LLM Code Generation Enables Verifiable AI Decision-Making
New research proposes replacing probabilistic LLM outputs with executable code, creating auditable decision trails that could transform AI system trustworthiness and interpretability.
Brittlebench: New Benchmark Measures LLM Fragility to Prompts
New research introduces Brittlebench, a systematic framework for quantifying how sensitive large language models are to minor prompt variations, revealing critical reliability gaps in AI systems.
Research Explores How Humans Assign Blame to AI Systems
New research investigates how people attribute causality to AI across scenarios of agency, misuse, and misalignment, with implications for accountability in synthetic media and deepfake governance.
York University Team Advances Audio Deepfake Detection Methods
York University's forensic speech science team earns recognition at major Deepfake Detection Challenge, advancing techniques for identifying synthetic audio and voice cloning fraud.
Nvidia DLSS 5 Brings Generative AI to Real-Time Gaming
Nvidia's DLSS 5 transforms from upscaler to generative AI filter, using neural rendering to create game frames in real-time with massive performance gains.
US Treasury Issues AI Risk Governance Guide for Banks
The US Treasury Department has released a comprehensive AI risk governance guidebook for financial institutions, addressing synthetic media threats, fraud detection, and responsible AI deployment in banking.
CoreWeave, Cerebras Partner on Canada's Largest AI Data Center
CoreWeave and Cerebras team up with BCE to build Canada's largest purpose-built AI data center, expanding critical compute infrastructure for AI model training and inference workloads.
Budget-Aware Value Tree Search Optimizes LLM Agent Reasoning
New research introduces Budget-Aware Value Tree Search (BA-VTS), a method that helps LLM agents reason more effectively while respecting computational budgets through intelligent search strategies.
Why High LLM Judge Scores Can Still Lead to Poor Model Selection
New research reveals a critical disconnect between LLM judge scores and Best-of-N selection outcomes, exposing systematic failures in how AI systems evaluate and choose between model outputs.
AI Firms Recruit Improv Actors to Train Emotional AI Systems
AI companies are partnering with improv actors to capture authentic human emotional expressions for training next-generation synthetic media systems capable of realistic emotional performance.